Yukai Zhou
- Don't Say No: Jailbreaking LLM by Suppressing Refusal
2024/04/25 by Yukai Zhou, Zhou, Yukai, Lou, Jian +4 · 10 citations
Social Sciences · Computer Science · #Legal Systems and Judicial Processes #Criminal Law and Evidence #Law, AI, and Intellectual Property
- How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions
2026/07/19 by Yukai Zhou, Feiyang Lu, Xiaokai Mao +2
#cs.CR #cs.CL